GPT-4O
GPT-4O is a chat model developed by OpenAI, capable of handling a wide range of tasks including code generation, reasoning, and text generation, with support for various input formats such as images, PDFs, and text. It is notable for its large context window of 128,000 tokens, allowing it to process and understand extensive amounts of information.
Input
Output
Context
128K
Max Output
16K
Parameters
200B
Technical Specifications
Model TypeChat
Context Window128,000 tokens
Max Output Tokens16,384 tokens
Parameters200B
Release DateMay 10, 2024
Training CutoffOct 1, 2023
Licenseproprietary
Open SourceNo
Input Modalities
ImageText
Output Modalities
Text
Capabilities
Benchmarks
Artificial Analysis
5.0%
HLE
32.7%
AIME
65.5%
GPQA
36.6%
SciCode
89.3%
MATH 500
80.3%
MMLU Pro
25.7
Math
42.5%
LiveCodeBench
12.3
Intelligence
Resources & Links
proprietary, Proprietary - API access only
Estimated GPU Requirements for GPT-4O
Estimates based on INT8 quantization. Actual requirements vary by framework and configuration.
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Jun 24, 2026
Start building with the right model.
Automatically route workloads to the right model for every task, every time.